Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NITISH-R-G/hackerrank-orchestrate-skills --skill orchestrate-input-validation-and-overridesgit clone --depth 1 https://github.com/NITISH-R-G/hackerrank-orchestrate-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-validation-and-overrides)<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-validation-and-overrides"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-validation-and-overrides/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-validation-and-overrides"><img src="https://agentmods.dev/badge/skills/nitish-r-g/hackerrank-orchestrate-skills/orchestrate-input-validation-and-overrides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.00855 |
| Opus 5 | $0.00046 | $0.00428 |
| Sonnet 5 | $0.00018 | $0.00171 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
orchestrate-input-validation-and-overrides scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate: Input Validation and Deterministic Overrides
Source: The Engineer's Notebook, "Getting better at HackerRank Orchestrate" (Shloka Shah) — names input validation before model calls as a distinct requirement from output validation after generation, and separately names "rule-based overrides for cases where model discretion shouldn't apply" as part of a reliable guardrail design. Reinforced by a first-hand #1-ranked participant case study (Medium, "How I went from 122 to 1"), which describes replacing a binary safety flag with a conditional, confidence-gated safety gate: a hard block fires only when the model cannot cite specific evidence, rather than automatically downgrading every verdict whenever a low-confidence signal appears — preventing legitimate findings from being silently overridden by noisy metadata.
Two validation layers, not one
orchestrate-schema-guardrails (already in this collection) covers validating model output against the expected schema. This skill covers the layer before that: validating input before it ever reaches a model call.
What input validation catches, specifically: empty or missing required fields, duplicate IDs across the dataset, malformed file references (an image path that doesn't resolve, a corpus document ID that doesn't exist), and — per the Orchestrate dataset's known design — prompt injection attempts embedded in ticket/claim text. Catching these before a model call means you're not spending a model call (and its cost/latency/failure surface) on an input you already know is broken, and you have a clean, deterministic place to log why a given input was rejected or routed differently.
When to override the model rather than ask it
Not every decision should be left to model discretion. The organizer guidance names this as a deliberate design choice: some cases warrant a rule-based override — a deterministic check that forces an outcome regardless of what the model would have said. Candidates for this:
- A structurally invalid input (missing required evidence, per the challenge's own schema) — escalate or reject by rule, don't ask the model to guess around a data problem.
- A confirmed prompt-injection pattern — route to escalation by rule once detected, rather than trusting the model to have resisted it (defense in depth: even a well-prompted model can be talked out of its instructions; a rule doesn't get talked out of anything).
- A case explicitly outside the domain the corpus covers — deterministic "insufficient grounding" rather than a generated guess.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 33 lines · 92 tokens per session scan A f7f5eacfc7b4
orchestrate-input-validation-and-overrides is a skill published in the GitHub repository NITISH-R-G/hackerrank-orchestrate-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 855 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
general
Handle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember something, or requests skill search and…
multi-bot
Coordinates responses between multiple GolemBot instances in a shared fleet. Use when the bot operates in a group chat with other bots, needs to decide whether to respond or pass, or must call a peer bot's API to fetch cross-domain data.
kb-guide
Search, read, create, and update knowledge base entries via MCP-connected KB tools. Use when the user asks to look up documentation, find existing articles, check if docs exist on a topic, create a new KB entry, update an existing document, or when domain questions should be answered from the knowledge base first.
ops
Content operations assistant — drafts blog posts, social media copy, and marketing materials, compiles data briefings, and tracks competitor activity. Use when the user asks to write a blog post, draft social media content, create marketing copy, generate a weekly report, compile operational metrics, update the…
escalation
Escalate unresolvable or sensitive requests to a human agent by recording an escalation entry. Use when the user asks to speak to a human, the bot cannot answer confidently, the request involves financial, legal, or security concerns, a safety issue is detected, or the user is frustrated after repeated failures.
code-review
Reviews code changes, pull requests, and diffs for correctness, security, performance, and style. Use when the user submits a PR for review, asks to review a diff or code snippet, or requests a quality check on recent changes.